feat: Enable prompt_embeds Content Part Support in vLLM Chat Completions API (#40720)

Signed-off-by: Luis Robaina <luis@protopia.ai>
Signed-off-by: Luis Robaina 🚀 <luisfabian1545@gmail.com>
Signed-off-by: LuisRobaina <luis@protopia.ai>
Co-authored-by: Andrew Sansom <qthequartermasterman@gmail.com>
This commit is contained in:
Luis 🚀
2026-05-01 10:05:55 +08:00
committed by GitHub
co-authored by Andrew Sansom
parent 1adaa5056b
commit 14043dfecd
28 changed files with 2301 additions and 82 deletions
+2
View File
@@ -38,6 +38,7 @@ class NewRequestData:
num_computed_tokens: int
lora_request: LoRARequest | None
prompt_embeds: "torch.Tensor | None" = None
prompt_is_token_ids: list[bool] | None = None
# Only used for v2 model runner.
prefill_token_ids: list[int] | None = None
@@ -59,6 +60,7 @@ class NewRequestData:
num_computed_tokens=request.num_computed_tokens,
lora_request=request.lora_request,
prompt_embeds=request.prompt_embeds,
prompt_is_token_ids=request.prompt_is_token_ids,
prefill_token_ids=prefill_token_ids,
)